{"uid":"cap_sYdh1ztHuql8qtGPp9sQj","slug":"x402broker-markdown-distill-html-to-markdown-semantic-distillation-facb0ba9","name":"x402broker Markdown Distill — HTML-to-Markdown Semantic Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://x402broker.com/v1/markdown-distill)","url":"https://x402broker.com/v1/markdown-distill?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bvkfASfALYP97T-G-0y9M","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_arnpHhoa0a0LsRTWHvdsB","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL and strips 85–97% of HTML token bloat, returning clean semantic markdown for LLM consumption","exampleAgentPrompt":"Can you fetch https://en.wikipedia.org/wiki/Artificial_intelligence and distill it down to clean markdown — strip all the HTML bloat so I can feed just the meaningful content to my LLM without burning through tokens?","exampleUseCases":[{"title":"LLM context window compression","prompt":"Grab the page at https://docs.openai.com/api-reference and convert it to stripped-down markdown so I can fit it into my prompt without wasting tokens on HTML tags and boilerplate."},{"title":"Agent web research pipeline","prompt":"Fetch https://techcrunch.com/2024/01/15/ai-agents-future/ and distill it to clean semantic markdown so my research agent can read just the article content without all the nav menus and ads."},{"title":"Automated content ingestion for RAG","prompt":"I need to pull in the content from https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany and strip it down to markdown — remove all the HTML noise so I can index just the meaningful text in my vector database."}],"resultDescription":"Returns clean, semantic markdown text representing the core content of the fetched URL, with 85–97% of HTML token bloat removed — including navigation, ads, boilerplate, and structural tags — leaving only meaningful textual content suitable for LLM ingestion.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error or empty content","JavaScript-rendered single-page applications may yield minimal content since the distiller fetches raw HTML","Paywalled or bot-protected pages may return access-denied content rather than the article body","Extremely large pages may hit processing limits or timeout","Invalid or malformed URL input causes request failure"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content into an LLM and want to minimize token usage by removing HTML structure, navigation, ads, and boilerplate. It is ideal for agent pipelines that need to ingest multiple URLs efficiently, for RAG ingestion workflows, or any scenario where raw HTML would waste significant context window space. Prefer this over raw fetch-and-parse approaches when you want semantic distillation rather than just tag stripping.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:19.136Z","isFirstParty":false,"canonicalSlug":"x402broker-markdown-distill-html-to-markdown-semantic-distillation-facb0ba9"}